// Runs in the page as a content script, after lib/Readability.js has already
// been injected (see background.js's executeScript files array — order matters).
// Its return value becomes the result of chrome.scripting.executeScript.
(() => {
  try {
    const docClone = document.cloneNode(true);
    const article = new Readability(docClone).parse();
    if (article && article.textContent && article.textContent.trim().length > 200) {
      return {
        url: location.href,
        title: article.title || document.title,
        content_html: article.content,
        content_text: article.textContent,
        author: article.byline || undefined,
        published_at: article.publishedTime || undefined,
      };
    }
  } catch (e) {
    // fall through to raw capture below
  }

  // Fallback: Readability either failed or returned too little to be useful
  // (common on heavily JS-rendered pages) — capture what's actually rendered
  // rather than failing outright. Worse capture beats no capture.
  return {
    url: location.href,
    title: document.title,
    content_html: document.body ? document.body.innerHTML : '',
    content_text: document.body ? document.body.innerText : '',
  };
})();